Git.Top Guide

Data Trust Guide

Use Git.Top coverage, quality governance, sync status, and confidence signals before trusting project recommendations.

Guide

Trust Checks

Check metadata source, corpus coverage, D1 availability, sync freshness, classification evidence, and quality signal confidence before making production decisions.

Guide

Operational Use

Operators and agents can combine /status, /coverage, /quality, /quality/review, and get_quality_report to understand data readiness and risk.

Data Source

d1 / d1_query

1215 loaded projects. Generated at 2026-09-04T15:03:17.488Z.

Evaluation package that allows benchmarking of agentic AIs from various sources and frameworks by producing statistical results which can be compared across different use cases and datasets.

Llm EvalLibrary OnlyLocalCloud
Quality6
Agent53

OpenTelemetry-native SDK for AI agent observability, tracing, evaluation, debugging, governance, and runtime policy enforcement. Framework-agnostic and built for OpenAI Agents, LangGraph, CrewAI, and LLM applications in production.

Llm EvalLibrary OnlyLocalCloud
Quality22
Agent61

The open-source governance layer for AI agents. No model in the coordination loop: parallel runs in per-task git worktrees replay byte-identically; signed lineage + an opt-in HMAC audit chain verify offline. Claude Code, Codex, Gemini CLI, +40 more. Any deliverable, code to audit evidence. Cluster mode, air-gap. Beta. https://bernstein.run

Workflow AutomationDockerLocalCloud
Quality52
Agent81

Project

modu-ai/moai-adk

67

Agentic development harness for Claude Code — SPEC-driven plan/run/sync, TRUST 5 quality gates, model+effort routing, and Claude×GLM multi-LLM cost control. Single Go binary, 16 languages, zero deps.

Coding AgentLocalCloud
Quality32
Agent67

Project

KbWen/agentic-os

60

Governance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.

Coding AgentLocalCloud
Quality25
Agent60

Project

qdrant/skills

60

Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage across Python, TypeScript, Rust, Go, .NET, Java

Ai ObservabilityLocalCloud
Quality15
Agent60

📚 A curated list of papers & technical articles on AI Quality & Safety

Llm EvalLibrary OnlyLocalCloud
Quality5
Agent54

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

Agent FrameworkDockerKubernetesServerless
Quality84
Agent88

Project

PrismorSec/prismor

72

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

Mcp ServerDockerVercelServerless
Quality33
Agent72

The best AI workforce platform, to build AI teams that actually deliver.

Workflow AutomationLibrary OnlyLocalCloud
Quality29
Agent65

Project

soapbucket/sbproxy

65

Open source Enterprise AI Gateway for API, MCP and agent, and AI model traffic. One Apache-2.0 binary: 72 native providers behind an OpenAI-compatible API, or serve vLLM and llama.cpp on your own GPUs. Keys, budgets, guardrails, semantic cache, WAF.

Mcp ServerDockerKubernetesLocal
Quality29
Agent65

Development workflows for Claude Code that keep broad exploration focused on the outcome you approved.

Workflow AutomationLibrary OnlyLocalCloud
Quality26
Agent66